mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-13 06:45:26 -04:00
Richard Palethorpe
799cc9f211
feat: bound backend admission and expose running traces Add process-wide backend execution admission without blocking UI or administrative HTTP work. Represent backend operations while they are in flight, surface running traces with immediate log links, and tie streaming admission leases to the gRPC receive lifecycle. Assisted-by: OpenAI Codex: GPT-5 Signed-off-by: Richard Palethorpe <io@richiejp.com>
77 lines
2.1 KiB
Go
77 lines
2.1 KiB
Go
package backend
|
|
|
|
import (
|
|
"time"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
"github.com/mudler/LocalAI/core/trace"
|
|
"github.com/mudler/LocalAI/pkg/grpc"
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
)
|
|
|
|
func ModelDetokenize(tokens []int32, loader *model.ModelLoader, modelConfig config.ModelConfig, appConfig *config.ApplicationConfig) (schema.DetokenizeResponse, error) {
|
|
|
|
var inferenceModel grpc.Backend
|
|
var err error
|
|
|
|
opts := ModelOptions(modelConfig, appConfig)
|
|
inferenceModel, err = loader.Load(opts...)
|
|
if err != nil {
|
|
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
|
|
return schema.DetokenizeResponse{}, err
|
|
}
|
|
|
|
release, err := AcquireGlobalBackendSlot()
|
|
if err != nil {
|
|
return schema.DetokenizeResponse{}, err
|
|
}
|
|
defer release()
|
|
var startTime time.Time
|
|
var traceID string
|
|
if appConfig.EnableTracing {
|
|
trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
|
|
startTime = time.Now()
|
|
traceID = trace.BeginBackendTrace(trace.BackendTrace{Timestamp: startTime, Type: trace.BackendTraceTokenize, ModelName: modelConfig.Name, Backend: modelConfig.Backend, Summary: "detokenize"})
|
|
}
|
|
defer trace.CancelBackendTrace(traceID)
|
|
|
|
resp, err := inferenceModel.Detokenize(appConfig.Context, &pb.DetokenizeRequest{Tokens: tokens})
|
|
|
|
if appConfig.EnableTracing {
|
|
errStr := ""
|
|
if err != nil {
|
|
errStr = err.Error()
|
|
}
|
|
|
|
content := ""
|
|
if resp != nil {
|
|
content = resp.Content
|
|
}
|
|
|
|
trace.RecordBackendTrace(trace.BackendTrace{
|
|
ID: traceID,
|
|
Timestamp: startTime,
|
|
Duration: time.Since(startTime),
|
|
Type: trace.BackendTraceTokenize,
|
|
ModelName: modelConfig.Name,
|
|
Backend: modelConfig.Backend,
|
|
Summary: trace.TruncateString(content, 200),
|
|
Error: errStr,
|
|
Data: map[string]any{
|
|
"token_count": len(tokens),
|
|
"output_text": trace.TruncateString(content, 1000),
|
|
},
|
|
})
|
|
}
|
|
|
|
if err != nil {
|
|
return schema.DetokenizeResponse{}, err
|
|
}
|
|
|
|
return schema.DetokenizeResponse{
|
|
Content: resp.Content,
|
|
}, nil
|
|
}
|